Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5955 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0000

Data Index: 15694 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1225474 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0048. Min Act: -0.0000

Data Index: 906887 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9379. Min Act: -0.0000

Data Index: 667151 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9717. Min Act: -0.0000

Data Index: 478033 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9634. Min Act: -0.0000

Data Index: 392716 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9044. Min Act: -0.0000

Data Index: 801585 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1214462 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1103059 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9090. Min Act: -0.0000

Data Index: 135939 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8190. Min Act: -0.0000

Data Index: 256643 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8417. Min Act: -0.0000

Data Index: 15388 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8140. Min Act: -0.0000

Data Index: 32431 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7948. Min Act: -0.0000

Data Index: 328343 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7424. Min Act: -0.0000

Data Index: 293882 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7753. Min Act: -0.0000

Data Index: 972240 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7502. Min Act: -0.0000

Data Index: 650943 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7419. Min Act: -0.0000

Data Index: 110100 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.6931. Min Act: -0.0000

Data Index: 2787 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7304. Min Act: -0.0000

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 680